AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Rethink Sparse Signals for Pose-guided Text-to-image Generation

Wenjie Xuan, Jing Zhang, Juhua Liu, Bo Du, Dacheng Tao

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 8 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add spatial-pose representation (ablation)ControlNet · AP-10Kpose mAP: 44.25 -> 52.85Improved
add keypoint concept learning (ablation)ControlNet · AP-10Kpose mAP: 44.25 -> 51.34Improved
combine both modules (ablation)ControlNet · AP-10Kpose mAP: 44.25 -> 55.63Improved
add keypoint concept learning on top of spatial pose (ablation)ControlNet · AP-10Kpose mAP: 52.85 -> 55.63Improved
add both modules (CLIP-Score cost)ControlNet · AP-10KCLIP-Score: 24.77 -> 23.86Hurt
use keypoint tokens at inference rather than removing them (ablation)SP-Ctrl · AP-10Kpose mAP: 45.07 -> 51.34Improved
learnable spatial embedding module vs fixed RGB OpenPose embeddings (ablation)ControlNet · AP-10Kpose mAPImproved
random vs text-embedding initialization of E0 (ablation)spatial-pose representation · AP-10Kpose mAP: 0.88% higher mAPImproved
all-ones skeleton embedding vs interpolation (ablation)spatial-pose representation · AP-10Kpose mAP: 0.86% higherImproved
all-ones skeleton embedding vs learnable vectors (ablation)spatial-pose representation · AP-10Kpose mAP: 1.96% higherImproved
vary embedding dimension C' (ablation)spatial-pose representation · AP-10Kpose mAPNo clear effect
apply heatmap loss at time steps 250-500 only (ablation)keypoint concept learning · AP-10Kpose mAPImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy